© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 531
    Prev
    Next
    INDEX
    Explanations

    brown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brown
    -1.06
     Brown
    -1.04
     brown
    -0.94
    brown
    -0.78
     BROWN
    -0.75
    BROWN
    -0.69
     marrón
    -0.48
     Apare
    -0.46
     коричне
    -0.46
    棕色
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.96
     estekak
    0.81
     članak
    0.78
    migrationBuilder
    0.74
    StoryboardSegue
    0.73
     Wiktionnaire
    0.73
     EconPapers
    0.69
    estinal
    0.68
    uscular
    0.67
    UnitTesting
    0.66
    Activations Density 0.226%

    No Known Activations